You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
### RAIN-GS: Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting
This method introduces three strategies to enhance 3D Gaussian splatting. First, it employs Sparse-Large-Variance (SLV) initialization, which begins with a small number of Gaussians to capture the overall structure of the point cloud. Second, progressive Gaussian low-pass filtering encourages initial large-scale Gaussians to cover wider areas. Third, the adaptive bound-expanding split (ABE-Split) algorithm moves Gaussians beyond their initial bounds, encouraging them to explore a broader space for more accurate geometry reconstruction.